config example

configinstance.py

input_dim = 5 #input dimension for the network, adapte this to your use case
output_dim = 1 #ouput dimension
layers_configs = [[2]] #you can have multiple layers configs, if you want multiple neural networks,
#for now this example will create a neural network with one hidden layer of two nodes.
#[[10, 5]] this will create a neural network with two hidden layers of 10 and 5 nodes respectively
#[[9],[3,2]] using this will create two configurations for two different networks

#ignore the rest of parameters, they are generic, we need them so the builder works fine
training_algorithms = ['rmsprop'] #you can specify multiple training algorithms each config will have one
losses = ['binary_crossentropy'] #you can also define one or more loss functions
dropouts = [1] # drop out is another algorithm to set
regularization = ['dropout', 'early'] #also this
regularizers_v = [regularizers.l2(0.)] #and this
hidden_activations = ['relu'] #specify activation function for hidden layers
output_activations = ['sigmoid'] #ouput activation function
callbacks = [] # any callbacks at the end of each epoch
metrics = ['binary_accuracy'] #error metric measurement
initializers = ['random_normal'] #initialization function
epochs = 100
batch_size = 1024